Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 725 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.2890. Min Act: -0.1700

Data Index: 912019 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.2419. Min Act: -0.1700

Data Index: 857011 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.2261. Min Act: -0.1700

Data Index: 415912 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.1474. Min Act: -0.1700

Data Index: 269189 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.1632. Min Act: -0.1700

Data Index: 53042 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.1474. Min Act: -0.1700

Data Index: 52401 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0844. Min Act: -0.1700

Data Index: 1235769 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0686. Min Act: -0.1700

Data Index: 970329 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.1159. Min Act: -0.1700

Data Index: 776104 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0844. Min Act: -0.1700

Data Index: 556233 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0686. Min Act: -0.1700

Data Index: 835611 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0371. Min Act: -0.1700

Data Index: 913992 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0371. Min Act: -0.1700

Data Index: 1192520 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0528. Min Act: -0.1700

Data Index: 576187 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0371. Min Act: -0.1700

Data Index: 1028394 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0055. Min Act: -0.1700

Data Index: 372771 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0213. Min Act: -0.1700

Data Index: 899408 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 3.2890. Min Range: -3.2890

Max Act: 2.9896. Min Act: -0.1700

Data Index: 251435 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0213. Min Act: -0.1700

Data Index: 703435 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 3.2890. Min Range: -3.2890

Max Act: 3.0055. Min Act: -0.1700

Data Index: 243745 (C4 (Web Text))

Max Activating Token Index: 764